An Improved Evaluation Framework for Generative Adversarial Networks

TL;DR

This paper introduces an enhanced evaluation framework for GANs that uses domain-specific features and a class-aware metric to provide more accurate and robust assessments of generated images, addressing limitations of existing methods like FID.

Contribution

The paper presents a novel evaluation framework with a specialized encoder and Class-Aware Frechet Distance, improving over FID in accuracy and robustness for domain-specific image generation.

Findings

The new framework outperforms FID in various experiments.

It detects inconsistencies in FID with human judgments.

The approach is more robust and domain-sensitive.

Abstract

In this paper, we propose an improved quantitative evaluation framework for Generative Adversarial Networks (GANs) on generating domain-specific images, where we improve conventional evaluation methods on two levels: the feature representation and the evaluation metric. Unlike most existing evaluation frameworks which transfer the representation of ImageNet inception model to map images onto the feature space, our framework uses a specialized encoder to acquire fine-grained domain-specific representation. Moreover, for datasets with multiple classes, we propose Class-Aware Frechet Distance (CAFD), which employs a Gaussian mixture model on the feature space to better fit the multi-manifold feature distribution. Experiments and analysis on both the feature level and the image level were conducted to demonstrate improvements of our proposed framework over the recently proposed state-of-the-art FID method. To our best knowledge, we are the first to provide counter examples where FID gives inconsistent results with human judgments. It is shown in the experiments that our framework is able to overcome the shortness of FID and improves robustness. Code will be made available.